Social Media Commons^™

Extracting Drug-Drug Interactions With Character-Level And Dependency-Based Embeddings, John Cardiff, Liliya Akhtyamova

Conference Papers

The DDI track of TAC-2018 challenge addresses the problem of an information retrieval of drug-drug interactions on structured product labeling documents with discontinuous and overlapping entities. In this paper, we present our participation for event extraction subtask (Task 1). We used a supervised long-short-term memory (LSTM) network with conditional random fields decoding (LSTM-CRF) approach with an automatic exploring of words and characters features. Additional dependency-based information was integrated into word embeddings to allow better word representation. Our system performed with above median score.

Comparing Elm With Svm In The Field Of Sentiment Classification Of Social Media Text Data, Zhihuan Chen, Zhaoxia Wang, Zhiping Lin, Ting Yang

Research Collection School Of Computing and Information Systems

Machine learning has been used in various fields with thousands of applications. Extreme learning machine (ELM), which is the most recently developed machine learning algorithm, has become increasingly popular for its good generalization ability. However, it has been relatively less applied to the domain of social media. Support Vector Machine (SVM), another popular learning-based algorithm, has been applied for sentiment classification of social media text data and has obtained good results. This paper investigates and compares the capabilities of these two learning-based methods in the field of sentiment classification of social media. The results indicate that SVM can obtain good …

Linky: Visualizing User Identity Linkage Results For Multiple Online Social Networks (Demo), Roy Ka-Wei Lee, Ming Shan Hee, Philips Kokoh Prasetyo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

User identity linkage across online social networks is an emerging research topic that has attracted attention in recent years. Many user identity linkage methods have been proposed so far and most of them utilize user profile, content and network information to determine if two social media accounts belong to the same person. In most cases, user identity linkage methods are evaluated by performing some prediction tasks with the results presented using some overall accuracy measures. However, the methods are rarely compared at the individual user level where a predicted matched (or linked) pair of user identities from different online social …

Tweeting The Ir, Paul Royster

DC-HUG '18

Social media has become an important means of keeping up to date for busy IR managers. Limited to short, pithy messages, but permitting linking and re-tweeting, the Twitter medium is both handy and powerful … when used appropriately. Alternatively, it can become a portal to fascinating, entertaining, horrifying, and time-consuming off-topic content and even an avenue for online harrassment. The presentation for DC-HUG will involve audience participation, and will include discussions of appropriate forms of identity, good and bad avatars, who to follow for scholarly communications subjects, whom to avoid for greater peace of mind, what are appropriate subjects, how …

Social Media For Good? A Survey On Millennials’ Inspirational Social Media Use, Sophie Janicke-Bowles, Ava Nayaran, Anja Seng

Communication Faculty Articles and Research

There is no doubt about the extensive use of social media by the millennial generation, but the study of the effects of such use is only in its infancy. Though most studies so far focus on the negative effects of overall time spent on social media, the current study investigated the relationship between exposure to a specific type of content on social media and well-being outcomes: namely, inspirational content. Results of an online survey with a total of 146 students revealed that inspiring social media and online video use, but not overall time spent on social media was related to …

The Media Effect And The Implications For Racial Minority Groups, Hailey E. Hoffman

Student Publications

The Media Effects Theory explains the impact media exposure can have on both the individual and societal level. Recent studies have shown that the increase in media consumption influences the perceptions an individual develops about their self and of other groups. The attitudes individuals develop become more susceptible to media influence when they are given smart technology starting in early childhood. The lack of diversity and negative stereotypes portrayed within the media magnifies the media effect experienced by minority users. The news, entertainment, fashion, and beauty industries are areas of the media that society has become particularly fixed on. These …

Millennials And The Increasing Use Of Social Media: Impact On The Employee Life Cycle, Sarah M. Pryor

Student Publications

The millennial generation is a generation of society that values technology, media, and connections, all three being equally important. This paper studies and theorizes the implications that social media has had on the workplace throughout the employee life cycle and how the traditional processes of this cycle have been altered. In the workforce, this aspect of the employee life cycle incorporates all different stages an employee goes through. From networking to being hired, to forming connections with co-workers, to working hard and performing well, to being fired, social media has impacted each stage of this cycle. Social media is a …

Transforming Library And Information Services Delivery Using Innovation Technologies, Ogar Christopher Eje Mr, Tangkat Yusuf Dushu Mr.

Library Philosophy and Practice (e-journal)

In todays’ world, library and information services delivery are being transformed from their manual operations to new ways using technology. The study identified the paradigm shift in libraries and information services as a direct consequence of innovation technologies. The key concepts in the study are discussed. The new technology and communication tools are employed in rendering services to the patrons through appropriate channels for access to information with cluster of technologies referred to as the internet. Information technology has brought in sweeping changes in the way libraries function. Libraries need to access, evaluate, and measure the impact of information technology …

The Role Of Snapchat In The Dynamics Of E-Commerce And Communication In Saudi Arabia, Hessah Alqahtani

Student Theses and Dissertations

This online survey sought to identify how Saudi Arabians use Snapchat as an e-commerce and communication tool. The Uses and Gratifications, and Diffusion of Innovation Theories were used to reach the study’s goals. The “Snowball” sampling method was used to target 486 participants. Saudi Snapchat users use it as a communication tool, as opposed to other social media that are used for online shopping and e-commerce. The majority of participants aged between 18 and 30 years (66.9%) use Snapchat. With advancing age, its use declines. A few Saudi people see Snapchat as an effective e-commerce platform. 20.9% use it for …

Operating A Digital Marketing Agency Out Of China, Singapore Management University

Perspectives@SMU

Mobile Now has to contend with the Great Firewall of China but the opportunities for growth outweigh the technical obstacles

Building Classifiers With Gmdh For Health Social Networks (Bd Askapatient), John Cardiff, Liliya Akhtyamova, Mikhail Alexandrov

Conference Papers

Health social media offer useful data for patients and doctors concerning both various medicines and treatments. Usually, these data are accompanied by their assessments in 5- star scale. But such a detail classification has small usefulness because patients and doctors, first of all, want to know about negative cases and to study in detail the extreme ones. In the paper we build classifiers of texts just for these cases using combined classes as negative, all others and worst, satisfactory, best. For this, we study possibilities of different GMDH-based algorithms and compare them with the results of other methods. The selection …

Classifying Misogynistic Tweets Using A Blended Model: The Ami Shared Task In Ibereval 2018, John Cardiff, Elena Shushkevich

Conference Papers

This article describes a possible solution for Automatic Misogyny Identification (AMI) Shared Task at IBEREVAL-2018. The proposed technique is based on combining several simpler classifiers into one more complex blended model, which classified the data taking into account the probabilities of belonging to classes calculated by simpler models. We used the Logistic Regression, Naive Bayes, and SVM classifiers. The experimental results show that blended model works better than simpler models for all three type of classification, for both binomial classification (Misogyny Identifivation, Target Classification) and multinomial classification (Misogynistic Behavior).

Diversity In Online Advertising: A Case Study Of 69 Brands On Social Media, Jisun An, Ingmar Weber

Research Collection School Of Computing and Information Systems

Lack of diversity in advertising is a long-standing problem. Despite growing cultural awareness and missed business opportunities, many minorities remain under- or inappropriately represented in advertising. Previous research has studied how people react to culturally embedded ads, but such work focused mostly on print media or television using lab experiments. In this work, we look at diversity in content posted by 69 U.S. brands on two social media platforms, Instagram and Facebook. Using face detection technology, we infer the gender, race, and age of both the faces in the ads and of the users engaging with ads. Using this dataset, …

Implicit Linking Of Food Entities In Social Media, Wen Haw Chong, Ee Peng Lim

Research Collection School Of Computing and Information Systems

Dining is an important part in people’s lives and this explains why food-related microblogs and reviews are popular in social media. Identifying food entities in food-related posts is important to food lover profiling and food (or restaurant) recommendations. In this work, we conduct Implicit Entity Linking (IEL) to link food-related posts to food entities in a knowledge base. In IEL, we link posts even if they do not contain explicit entity mentions. We first show empirically that food venues are entity-focused and associated with a limited number of food entities each. Hence same-venue posts are likely to share common food …

Qualitative Research On Youths’ Social Media Use: A Review Of The Literature, Mardi Schmeichel, Hilary E. Hughes, Mel Kutner

Department of Teaching, Learning, and Teacher Education: Faculty Publications

In this article we explore how educational researchers report empirical qualitative research about young people’s social media use. We frame the overall study with an understanding that social media sites contribute to the production of neoliberal subjects, and we draw on Foucauldian discourse theories and the understanding that how researchers explain topics and concepts produces particular ways of thinking about the world while excluding others. Findings include that: (1) there is an absence of attention to the structure and function of social media platforms; (2) adolescents are positioned in problematic, developmental ways; and (3) the over-representation of girls and young …

Empowering With Prep (E-Prep), A Peer-Led Social Media–Based Intervention To Facilitate Hiv Preexposure Prophylaxis Adoption Among Young Black And Latinx Gay And Bisexual Men: Protocol For A Cluster Randomized Controlled Trial, Viraj V. Patel, Zoë Ginsburg, Sarit A. Golub, Keith J. Horvath, Nataly Rios, Kenneth H. Mayer, Ryunh S. Kim, Julia H. Arnsten

Publications and Research

Background: Young black and Latinx, gay, bisexual, and other men who have sex with men (YBLGBM, aged 18-29 years) have among the highest rates of new HIV infections in the United States and are not consistently reached by existing prevention interventions. Preexposure prophylaxis (PrEP), an oral antiretroviral regimen taken daily by HIV-uninfected individuals to prevent HIV acquisition, is highly efficacious in reducing HIV acquisition and could help stop the HIV epidemic in YBLGBM. Use of social media (eg, Facebook, Twitter, online dating sites) is ubiquitous among young people, providing an efficient avenue to engage YBLGBM to facilitate PrEP adoption.

Objective: …

Miss Representación: An Analysis Of Latino Feminism And Men, Isabel M. Velez

WRIT: Journal of First-Year Writing

Analysis of why feminism brings forth negative connotations and how feminism effects men from a latino standpoint. I've sought out to determine what are the causes of negativity towards different forms of feminism, understand what feminism is, and how to resolve the issue of misrepresentation in the media.

Essays On Performance Implications Of Social Media For Established And Nascent Firms, Alireza Golmohammadi

Graduate Theses and Dissertations

The possibility of large-scale communication with stakeholders brought about by social media has made these new channels of communication an important arena for spending marketing budgets. Despite the increasing share of social media in firms’ marketing budget, there is significant heterogeneity in firms’ social media communication practices even within the same venue and among firms from the same industry. As such, there is need for more research on how firms can leverage social media to achieve better performance. In order to address this broad question, two essays have been designed and executed.

The first essay utilizes integrated marketing communication as …

Facebook Intensity Use Related To Gender Identity And Self-Esteem Among Female College Students, Li Zhang

Masters Theses

As a popular social media platform, Facebook has already become a vital part of college students’ social lives. The purpose of this study is to explore the relationships among Facebook use, gender identity and the level of self-esteem among young female college students (from age 18 to 23). Previous studies have argued that Facebook has the ability to enhance or reshape gender identity by providing control over online self-presentation. In addition, by using Facebook intensively and frequently, users gain popularity (a larger network of Facebook friends), which also increases users’ self-esteem and the feeling of being connected with others. In …

Architecture Of Aggression In Cyberspace. Testing Cyber Aggression In Young Adults In Hungary, Katalin Parti, Tibor Kiss, Gergely Koplányi

International Journal of Cybersecurity Intelligence & Cybercrime

In order to test whether and how violence is exacerbated in online social networking sites, we utilized the BryantSmith Aggression Scale (Bryant & Smith, 2001), and included examples in the questionnaire offering solutions for 7 different hypothetical cases occurring online (Kiss, 2017). The questionnaire was sent to social work and law school students in Hungary. Prevalence and levels of aggression and its manifestation as violence online proved to be not more severe than in offline social relations. Law students were more aware than students of social work that online hostile acts are discrediting. Students of social work were significantly more …